{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:K52VUFP5FW6NMBKE4SHDVTBHFE","short_pith_number":"pith:K52VUFP5","canonical_record":{"source":{"id":"2004.09395","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-20T15:49:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9dd433d91d91fdf6d4ce9168440101e020ab5e389baf6bf57de53edfbd311f52","abstract_canon_sha256":"41c5e19e539d99fa8e175e63b055268af0b6bf8ea9a220f01da6b839f2990b42"},"schema_version":"1.0"},"canonical_sha256":"57755a15fd2dbcd60544e48e3acc27293c4dc29bed6c9f85f2c2188c0093fb1e","source":{"kind":"arxiv","id":"2004.09395","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.09395","created_at":"2026-07-05T02:32:12Z"},{"alias_kind":"arxiv_version","alias_value":"2004.09395v4","created_at":"2026-07-05T02:32:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.09395","created_at":"2026-07-05T02:32:12Z"},{"alias_kind":"pith_short_12","alias_value":"K52VUFP5FW6N","created_at":"2026-07-05T02:32:12Z"},{"alias_kind":"pith_short_16","alias_value":"K52VUFP5FW6NMBKE","created_at":"2026-07-05T02:32:12Z"},{"alias_kind":"pith_short_8","alias_value":"K52VUFP5","created_at":"2026-07-05T02:32:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:K52VUFP5FW6NMBKE4SHDVTBHFE","target":"record","payload":{"canonical_record":{"source":{"id":"2004.09395","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-20T15:49:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9dd433d91d91fdf6d4ce9168440101e020ab5e389baf6bf57de53edfbd311f52","abstract_canon_sha256":"41c5e19e539d99fa8e175e63b055268af0b6bf8ea9a220f01da6b839f2990b42"},"schema_version":"1.0"},"canonical_sha256":"57755a15fd2dbcd60544e48e3acc27293c4dc29bed6c9f85f2c2188c0093fb1e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:12.818304Z","signature_b64":"ORf8FTSM4fl/vGz/ggG5XRdCOvgYBZMlWQnX7037LHAS8KDp4hJ87uimg1gKNdk1IwLDO2LJ6ojv4kFOGpMlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57755a15fd2dbcd60544e48e3acc27293c4dc29bed6c9f85f2c2188c0093fb1e","last_reissued_at":"2026-07-05T02:32:12.817802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:12.817802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.09395","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:32:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZGDZhqVClfOVVhCPlaNhGdPnaVBO3QpSrY0LuFgtyIKqGbPzuNh9Z9YsAJeLGB1tu+Ms0rSaYNER2zqObPnwCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:14:36.226268Z"},"content_sha256":"a77752bf09ec27a8d4aaf1aae3b1f48b590acca729d7a05f3b92cc0bb0d8fb13","schema_version":"1.0","event_id":"sha256:a77752bf09ec27a8d4aaf1aae3b1f48b590acca729d7a05f3b92cc0bb0d8fb13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:K52VUFP5FW6NMBKE4SHDVTBHFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Energy-Based Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Minghuan Liu, Minkai Xu, Tairan He, Weinan Zhang","submitted_at":"2020-04-20T15:49:35Z","abstract_excerpt":"We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals. Except the simple Behavior Cloning (BC) that adopts supervised learning followed by the problem of compounding error, previous solutions like inverse reinforcement learning (IRL) and recent generative adversarial methods involve a bi-level or alternating optimization for updating the reward function and the policy, suffering from high computational cost and training instability. Inspired by recent p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.09395","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.09395/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:32:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r6ohr0UVAj/4ZtGKbZKsolVpjzUopDpN/aEQDhrBRKI9WnoQD7EPNh8fC2QL5nVQIAtmei4gXgnKFRPgDVXLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:14:36.226931Z"},"content_sha256":"0726139c56bc18b8ff7abd687454a645d7d7e7705611eb440e9ce49c34f4fd33","schema_version":"1.0","event_id":"sha256:0726139c56bc18b8ff7abd687454a645d7d7e7705611eb440e9ce49c34f4fd33"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K52VUFP5FW6NMBKE4SHDVTBHFE/bundle.json","state_url":"https://pith.science/pith/K52VUFP5FW6NMBKE4SHDVTBHFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K52VUFP5FW6NMBKE4SHDVTBHFE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-05T13:14:36Z","links":{"resolver":"https://pith.science/pith/K52VUFP5FW6NMBKE4SHDVTBHFE","bundle":"https://pith.science/pith/K52VUFP5FW6NMBKE4SHDVTBHFE/bundle.json","state":"https://pith.science/pith/K52VUFP5FW6NMBKE4SHDVTBHFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K52VUFP5FW6NMBKE4SHDVTBHFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:K52VUFP5FW6NMBKE4SHDVTBHFE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"41c5e19e539d99fa8e175e63b055268af0b6bf8ea9a220f01da6b839f2990b42","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-20T15:49:35Z","title_canon_sha256":"9dd433d91d91fdf6d4ce9168440101e020ab5e389baf6bf57de53edfbd311f52"},"schema_version":"1.0","source":{"id":"2004.09395","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.09395","created_at":"2026-07-05T02:32:12Z"},{"alias_kind":"arxiv_version","alias_value":"2004.09395v4","created_at":"2026-07-05T02:32:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.09395","created_at":"2026-07-05T02:32:12Z"},{"alias_kind":"pith_short_12","alias_value":"K52VUFP5FW6N","created_at":"2026-07-05T02:32:12Z"},{"alias_kind":"pith_short_16","alias_value":"K52VUFP5FW6NMBKE","created_at":"2026-07-05T02:32:12Z"},{"alias_kind":"pith_short_8","alias_value":"K52VUFP5","created_at":"2026-07-05T02:32:12Z"}],"graph_snapshots":[{"event_id":"sha256:0726139c56bc18b8ff7abd687454a645d7d7e7705611eb440e9ce49c34f4fd33","target":"graph","created_at":"2026-07-05T02:32:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.09395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals. Except the simple Behavior Cloning (BC) that adopts supervised learning followed by the problem of compounding error, previous solutions like inverse reinforcement learning (IRL) and recent generative adversarial methods involve a bi-level or alternating optimization for updating the reward function and the policy, suffering from high computational cost and training instability. Inspired by recent p","authors_text":"Minghuan Liu, Minkai Xu, Tairan He, Weinan Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-20T15:49:35Z","title":"Energy-Based Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.09395","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a77752bf09ec27a8d4aaf1aae3b1f48b590acca729d7a05f3b92cc0bb0d8fb13","target":"record","created_at":"2026-07-05T02:32:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"41c5e19e539d99fa8e175e63b055268af0b6bf8ea9a220f01da6b839f2990b42","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-20T15:49:35Z","title_canon_sha256":"9dd433d91d91fdf6d4ce9168440101e020ab5e389baf6bf57de53edfbd311f52"},"schema_version":"1.0","source":{"id":"2004.09395","kind":"arxiv","version":4}},"canonical_sha256":"57755a15fd2dbcd60544e48e3acc27293c4dc29bed6c9f85f2c2188c0093fb1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57755a15fd2dbcd60544e48e3acc27293c4dc29bed6c9f85f2c2188c0093fb1e","first_computed_at":"2026-07-05T02:32:12.817802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:12.817802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ORf8FTSM4fl/vGz/ggG5XRdCOvgYBZMlWQnX7037LHAS8KDp4hJ87uimg1gKNdk1IwLDO2LJ6ojv4kFOGpMlAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:12.818304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.09395","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a77752bf09ec27a8d4aaf1aae3b1f48b590acca729d7a05f3b92cc0bb0d8fb13","sha256:0726139c56bc18b8ff7abd687454a645d7d7e7705611eb440e9ce49c34f4fd33"],"state_sha256":"551abc7ddec42407bef898f37948b547a3a584866bbaa81bdec4d0d72b16c4bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qs0KmWSUrNVV38+qL4ZoZ4DQfRgoyIZC77LwFZkAYp1xPikHW0SBz2b36fjI+Ibm06CNb4WC45F1pcjKl6t7Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T13:14:36.229956Z","bundle_sha256":"ad191f6e73ab00aeea42e61930adb7df5409c981d6852fe82eac33b6dd0ce29b"}}